Parallel

Tool to add an enrichment to a FindAll run. Use when you need to enrich existing FindAll run results with additional structured data fields. Enrichments define what information to extract from matched entities using a JSON schema.

Tool to initiate multiple task runs within a TaskGroup. Use when you need to execute multiple tasks in parallel within an existing task group.

Tool to cancel an active FindAll run by findall_id. Use when you need to stop a running FindAll operation before it completes. Cannot cancel runs that have already terminated.

Tool to get realtime chat completions from Parallel AI. Use when you need conversational AI responses or structured outputs via chat interface. Can be combined with Task API processors for research-grade structured outputs with citations and reasoning.

Tool to create a web monitor that periodically runs the specified query. The monitor runs once at creation and then continues according to the specified cadence (hourly, daily, weekly, or every two weeks). Use when you need to track changes or developments for a specific search query over time.

Tool to create a new task group. Use when batching multiple tasks for parallel execution. Task Groups enable grouping and tracking of multiple task runs within a single manageable unit.

Tool to create and initiate a task run. Returns immediately with a run object in status 'queued'. Use when you need to execute tasks asynchronously with Parallel AI processors.

Tool to delete a monitor, stopping all future executions. Use when you need to permanently remove a monitor. Deleted monitors can no longer be updated or retrieved.

Tool to extend a FindAll run by adding additional matches to the current match limit. Use when you need to increase the number of matches for an existing FindAll run that is still active or has completed.

Tool to extract relevant content from specific web URLs. Use when you need to fetch and extract content from known URLs with optional focusing on specific objectives or search queries.

Extract excerpts or full content from known web URLs with Parallel's current stable Extract API. Prefer this action over PARALLEL_EXTRACT, which uses the legacy beta API. The call is synchronous, so no polling is needed. Extraction costs $1 per 1,000 URLs, with at most 20 URLs per request. Typical latency is 1 to 20 seconds. The default limit is 600 POST requests per minute, and Parallel documents no provider concurrency ceiling.

Tool to retrieve task runs from a Task Group as a resumable stream. Use when you need to fetch all runs within a group, optionally including their inputs and outputs. The stream can be resumed using the event_id as a cursor.

Tool to start a FindAll run. Use when you need to discover and match entities based on natural-language objectives. Supports custom conditions, exclusion lists, and webhook callbacks.

Generate a synchronous answer grounded in live web research with URL citation annotations. Successful requests cost $10, $50, or $250 per 1,000 responses at low, medium, or high reasoning effort. Approximate completion times are 5-10, 15-20, or 30-60 seconds respectively. The result is returned synchronously in one call; no polling is required. Provider default rate and concurrency ceilings are not documented.

Tool to fetch the final (or latest available) FindAll candidates and result payload for a run. Use when you need to retrieve matched/unmatched candidates after a FindAll run has progressed or completed.

Tool to retrieve the schema configuration of a FindAll run by findall_id. Use when you need to inspect the objective, entity type, match conditions, and other schema details for a previously created FindAll run.

Retrieve a monitor's configuration and runtime state by ID using Parallel's current stable Monitor API. Prefer this action over PARALLEL_RETRIEVE_MONITOR, which uses the legacy alpha API. Reads do not execute checks and therefore do not incur documented check pricing. Monitor executions cost $3 per 1,000 checks with the lite processor or $10 per 1,000 checks with the base processor. The general rate-limit page says GET reads do not count against creation limits and documents 300 requests per minute only for legacy monitor POSTs, so no current GET rate is asserted here. The provider documents no concurrency ceiling.

Retrieve a current stable-API snapshot of a Task Group's aggregate run counts and status. Prefer this action over PARALLEL_RETRIEVE_TASK_GROUP, which uses the legacy beta API. If status.is_active is true, call this action again later to observe terminal status. This GET creates no billable Task run; task runs themselves cost by processor from $5-$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.

Tool to transform a natural language search objective into a structured FindAll specification. Use when you need to generate a FindAll run spec from a user's natural language description. The generated specification serves as a suggested starting point and can be further customized.

List monitors from Parallel's current stable Monitor API, newest first, with optional type and status filters. Prefer this action over PARALLEL_LIST_MONITORS, which uses the legacy alpha API. Reads do not execute checks and therefore do not incur documented check pricing. Monitor executions cost $3 per 1,000 checks with the lite processor or $10 per 1,000 checks with the base processor. This operation is cursor-paginated; callers poll by passing next_cursor as cursor only when another page is needed. The general rate-limit page says GET reads do not count against creation limits and documents 300 requests per minute only for legacy monitor POSTs, so no current GET rate is asserted here. The provider documents no concurrency ceiling.

Tool to list events for a monitor from up to the last 300 event groups. Retrieves events including errors and material changes in reverse chronological order.

Tool to list active monitors for the user. Returns all monitors regardless of status with their configuration and current state. Supports cursor-based pagination using monitor_id and limit parameters.

Collect Task Group runs from the current stable API's resumable event stream, optionally including structured inputs and outputs. Prefer this action over PARALLEL_FETCH_TASK_GROUP_RUNS, which uses the legacy beta API. Collection is bounded to 90 seconds, 1,000 events, and 3 MB; when truncated is true, pass the returned last_event_id to resume. This GET creates no billable Task run; task runs themselves cost by processor from $5-$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.

Collect progress and state events from a Task Run using the current stable API. Prefer this action over PARALLEL_STREAM_TASK_RUN_EVENTS, which uses the legacy beta API. Collection is bounded to 90 seconds, 1,000 events, and 3 MB and fails rather than returning an incomplete event history when a bound is reached. This GET creates no billable Task run; task runs themselves cost by processor from $5-$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.

Tool to retrieve an event group for a monitor. Use when you have a valid monitor ID and event group ID and want to view the execution history.

Tool to retrieve status and metadata for a FindAll run by findall_id. Use when you need to poll or check the progress of a FindAll run that was previously created.

Retrieve relevant memories ranked against a query, or recent memories when the query is empty or omitted. The provider documents no operation-specific pricing, default rate limit, or concurrency limit. Retrieval is synchronous and returns in one call; no polling is required.

Tool to retrieve a specific monitor by ID. Returns the monitor configuration including status, cadence, query, and webhook settings.

Tool to retrieve details of a specific task group. Use when you have a valid task group ID and want to view its details.

Tool to retrieve run status by run_id for a task group. Use when you need to check the status of a specific task group run or poll for completion.

Tool to retrieve run status by run_id. Use when you need to check the status or details of a specific task run. The run result is available from the /result endpoint.

Tool to retrieve the input data of a specific task run by run_id. Use when you need to view the original input parameters that were provided to a task run.

Tool to retrieve the result of a task run by run_id, blocking until the run completes. Use when you need to wait for and fetch the final output of a previously initiated task run. The request will block until the run completes or the timeout is reached.

Tool to perform parallel semantic search. Use when you need to retrieve top matching documents for multiple queries in a single call.

Search the web with Parallel's current stable Search API and return ranked results with markdown excerpts. Prefer this action over PARALLEL_SEARCH, which uses the legacy beta API. The call is synchronous, so no polling is needed. Turbo and Fast cost $1 per 1,000 requests. Basic and Advanced cost $5 per 1,000 requests including 10 results, with extra results at $1 per 1,000. Typical latency is 200 ms to 3 seconds. The default limit is 600 POST requests per minute, and Parallel documents no provider concurrency ceiling.

Tool to simulate sending an event for a monitor. Use when testing monitor webhooks or validating monitor configurations. Simulates sending an event of the specified type (defaults to monitor.event.detected).

Tool to stream events from a FindAll run. Use when you need real-time updates on candidate discovery, matching progress, and run status.

Tool to stream events for a Task Group. Use when you want real-time updates of group status and run completions.

Tool to stream events for a Task Run. Returns progress updates and state changes for the task run. For runs without enable_events=true, event frequency is reduced.

Tool to suggest tasks based on user intent. Use when you need task specifications generated from a natural language description of what you want to accomplish.

Tool to update a monitor's configuration. Use when you need to modify an existing monitor's cadence, query, metadata, or webhook settings. At least one field must be non-null to apply an update.